Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1150. Min Range: -9.1150
Max Act: 9.1150. Min Act: -0.1700
Data Index: 4961543 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.9275. Min Act: -0.1700
Data Index: 3045089 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.9275. Min Act: -0.1700
Data Index: 3045088 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8650. Min Act: -0.1700
Data Index: 8352856 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 7472965 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 1160702 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 741976 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 1672862 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 2191841 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.8025. Min Act: -0.1700
Data Index: 1890168 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 6441928 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 2158069 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 7306474 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 7313915 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 5629572 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 5489024 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 7866753 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 3911162 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 5362758 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1150. Min Range: -9.1150
Max Act: 8.7400. Min Act: -0.1700
Data Index: 104087 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19